Armin Hornung

Humanoid robot localization in complex indoor environments

In this paper, we present a localization method for humanoid robots navigating in arbitrary complex indoor environments using only onboard sensing. Reliable and accurate localization for humanoid robots operating in such environments is a challenging task. First, humanoids typically execute motion commands rather inaccurately and odometry can be estimated only very roughly. Second, the observations of the small and lightweight sensors of most humanoids are seriously affected by noise. Third, since most humanoids walk with a swaying motion and can freely move in the environment, e.g., they are not forced to walk on flat ground only, a 6D torso pose has to be estimated. We apply Monte Carlo localization to globally determine and track a humanoids 6D pose in a 3D world model, which may contain multiple levels connected by staircases. To achieve a robust localization while walking and climbing stairs, we intergrate 2D laser range measurements as well as attitude data and information from the joint encoders. We present simulated as well as real-word experiments with our humanoid and thoroughly evaluate our approach. As the experiments illustrate, the robot is able to globally localize itself and accurately track its 6D pose over time.

Real-time navigation in 3D environments based on depth camera data

In this paper, we present an integrated approach for robot localization, obstacle mapping, and path planning in 3D environments based on data of an onboard consumer-level depth camera. We rely on state-of-the-art techniques for environment modeling and localization, which we extend for depth camera data. We thoroughly evaluated our system with a Nao humanoid equipped with an Asus Xtion Pro Live depth camera on top of the humanoids head and present navigation experiments in a multi-level environment containing static and non-static obstacles. Our approach performs in real-time, maintains a 3D environment representation, and estimates the robots pose in 6D. As our results demonstrate, the depth camera is well-suited for robust localization and reliable obstacle avoidance in complex indoor environments.

Navigation in three-dimensional cluttered environments for mobile manipulation

Collision-free navigation in cluttered environments is essential for any mobile manipulation system. Traditional navigation systems have relied on a 2D grid map projected from a 3D representation for efficiency. This approach, however, prevents navigation close to objects in situations where projected 3D configurations are in collision within the 2D grid map even if actually no collision occurs in the 3D environment. Accordingly, when using such a 2D representation for planning paths of a mobile manipulation robot, the number of planning problems which can be solved is limited and suboptimal robot paths may result. We present a fast, integrated approach to solve path planning in 3D using a combination of an efficient octree-based representation of the 3D world and an anytime search-based motion planner. Our approach utilizes a combination of multi-layered 2D and 3D representations to improve planning speed, allowing the generation of almost real-time plans with bounded sub-optimality. We present extensive experimental results with the two-armed mobile manipulation robot PR2 carrying large objects in a highly cluttered environment. Using our approach, the robot is able to efficiently plan and execute trajectories while transporting objects, thereby often moving through demanding, narrow passageways.

Anytime search-based footstep planning with suboptimality bounds

Efficient footstep planning for humanoid navigation through cluttered environments is still a challenging problem. Many obstacles create local minima in the search space, forcing heuristic planners such as A* to expand large areas. The goal of this work is to efficiently compute long, feasible footstep paths. For navigation, finding the optimal path initially is often not needed as it can be improved while walking. Thus, we propose anytime search-based planning using the anytime repairing A* (ARA*) and randomized A* (R*) planners. This allows to obtain efficient paths with provable suboptimality within short planning times. Opposed to completely randomized methods such as rapidly-exploring random trees (RRTs), these planners create paths that are goal-directed and guaranteed to be no more than a certain factor longer than the optimal solution. We thoroughly evaluated the planners in various scenarios using different heuristics. ARA* with the 2D Dijkstra heuristic yields fast and efficient solutions but its potential inadmissibility results in non-optimal paths for some scenarios. R*, on the other hand borrows ideas from RRTs, yields fast solutions, and is less dependent on a well-designed heuristic function. This allows it to avoid local minima and reduces the number of expanded states.

From 3D point clouds to climbing stairs: A comparison of plane segmentation approaches for humanoids

In this paper, we consider the problem of building 3D models of complex staircases based on laser range data acquired with a humanoid. These models have to be sufficiently accurate to enable the robot to reliably climb up the staircase. We evaluate two state-of-the-art approaches to plane segmentation for humanoid navigation given 3D range data about the environment. The first approach initially extracts line segments from neighboring 2D scan lines, which are successively combined if they lie on the same plane. The second approach estimates the main directions in the environment by randomly sampling points and applying a clustering technique afterwards to find planes orthogonal to the main directions. We propose extensions for this basic approach to increase the robustness in complex environments which may contain a large number of different planes and clutter. In practical experiments, we thoroughly evaluate all methods using data acquired with a laser-equipped Nao robot in a multi-level environment. As the experimental results show, the reconstructed 3D models can be used to autonomously climb up complex staircases.

Humanoid navigation with dynamic footstep plans

Humanoid robots possess the capability of stepping over or onto objects, which distinguishes them from wheeled robots. When planning paths for humanoids, one therefore should consider an intelligent placement of footsteps instead of choosing detours around obstacles. In this paper, we present an approach to optimal footstep planning for humanoid robots. Since changes in the environment may appear and a humanoid may deviate from its originally planned path due to imprecise motion execution or slippage on the ground, the robot might be forced to dynamically revise its plans. Thus, efficient methods for planning and replanning are needed to quickly adapt the footstep paths to new situations. We formulate the problem of footstep planning so that it can be solved with the incremental heuristic search method D* Lite and present our extensions, including continuous footstep locations and efficient collision checking for footsteps. In experiments in simulation and with a real Nao humanoid, we demonstrate the effectiveness of the footstep plans computed and revised by our method. Additionally, we evaluate different footstep sets and heuristics to identify the ones leading to the best performance in terms of path quality and planning time. Our D* Lite algorithm for footstep planning is available as open source implementation.

Whole-body motion planning for manipulation of articulated objects

Humanoid service robots performing complex object manipulation tasks need to plan whole-body motions that satisfy a variety of constraints: The robot must keep its balance, self-collisions and collisions with obstacles in the environment must be avoided and, if applicable, the trajectory of the end-effector must follow the constrained motion of a manipulated object in Cartesian space. These constraints and the high number of degrees of freedom make whole-body motion planning for humanoids a challenging problem. In this paper, we present an approach to whole-body motion planning with a focus on the manipulation of articulated objects such as doors and drawers. Our approach is based on rapidly-exploring random trees in combination with inverse kinematics and considers all required constraints during the search. Models of articulated objects hereby generate hand poses for sampled configurations along the trajectory of the object handle. We thoroughly evaluated our planning system and present experiments with a Nao humanoid opening a drawer, a door, and picking up an object. The experiments demonstrate the ability of our framework to generate solutions to complex planning problems and furthermore show that these plans can be reliably executed even on a low-cost humanoid platform.

Autonomous climbing of spiral staircases with humanoids

In this paper, we present an approach to enable a humanoid robot to autonomously climb up spiral staircases. This task is substantially more challenging than climbing straight stairs since careful repositioning is needed. Our system globally estimates the pose of the robot, which is subsequently refined by integrating visual observations. In this way, the robot can accurately determine its relative position with respect to the next step. We use a 3D model of the environment to project edges corresponding to stair contours into monocular camera images. By detecting edges in the images and associating them to projected model edges, the robot is able to accurately locate itself towards the stairs and to climb them. We present experiments carried out with a Nao humanoid equipped with a 2D laser range finder for global localization and a low-cost monocular camera for short-range sensing. As we show in the experiments, the robot reliably climbs up the steps of a spiral staircase.

Improved proposals for highly accurate localization using range and vision data

In order to successfully climb challenging stair-cases that consist of many steps and contain difficult parts, humanoid robots need to accurately determine their pose. In this paper, we present an approach that fuses the robots observations from a 2D laser scanner, a monocular camera, an inertial measurement unit, and joint encoders in order to localize the robot within a given 3D model of the environment. We develop an extension to standard Monte Carlo localization (MCL) that draws particles from an improved proposal distribution to obtain highly accurate pose estimates. Furthermore, we introduce a new observation model based on chamfer matching between edges in camera images and the environment model. We thoroughly evaluate our localization approach and compare it to previous techniques in real-world experiments with a Nao humanoid. The results show that our approach significantly improves the localization accuracy and leads to a considerably more robust robot behavior. Our improved proposal in combination with chamfer matching can be generally applied to improve a range-based pose estimate by a consistent matching of lines obtained from vision.

Learning reliable and efficient navigation with a humanoid

Reliable and efficient navigation with a humanoid robot is a difficult task. First, the motion commands are executed rather inaccurately due to backlash in the joints or foot slippage. Second, the observations are typically highly affected by noise due to the shaking behavior of the robot. Thus, the localization performance is typically reduced while the robot moves and the uncertainty about its pose increases. As a result, the reliable and efficient execution of a navigation task cannot be ensured anymore since the robots pose estimate might not correspond to the true location. In this paper, we present a reinforcement learning approach to select appropriate navigation actions for a humanoid robot equipped with a camera for localization. The robot learns to reach the destination reliably and as fast as possible, thereby choosing actions to account for motion drift and trading off velocity in terms of fast walking movements against accuracy in localization. We present extensive simulated and practical experiments with a humanoid robot and demonstrate that our learned policy significantly outperforms a hand-optimized navigation strategy.